FRD: Few-shot rumor detection for the novel coronavirus pneumonia epidemic

With the full arrival of the digital era, fueled by both information technology and business marketing, rumors are produced and spread endlessly on social networks. During the recent novel coronavirus pneumonia epidemic, online rumors have continued to flourish. Most existing studies on traditional rumor detection rely on a large number of features in practical applications. However, the current severe epidemic scenarios have limited rumor information features, and it remains a challenging problem to detect epidemic rumors with high accuracy using only limited information. As a result, we propose a novel Few-shot Rumor Detection model (FRD) for the novel coronavirus pneumonia, which is combined with meta-learning to be able to accurately identify rumors as soon as possible in crises. Specifically, we started by using the BERT+BiLSTM combination for rumor text feature extraction and representation to generate the historical rumor sample-wise vector and epidemic rumor sample-wise vector; secondly, the prototypical network was introduced to summarize the historical rumor data, and the feature vectors of samples belonging to the same category were averaged to obtain the prototype representation of historical rumor category; finally, we utilize the modified cosine similarity measure function to calculate the distance between the class-wise vector of historical rumor text and the sample-wise vector of epidemic rumor, and complete the rumor detection according to the nearest neighbor method. Our experimental results on English datasets show that the FRD rumor detection model proposed in this paper is superior to other baseline algorithms in terms of accuracy, precision, recall and macro F1 value. From the comparison of experimental results, the FRD model can effectively improve conventional rumor detection methods, and better realize the early detection of sudden epidemic rumors.